Groq MCP Server

🚀 Groq MCP Server

This project is a Model Context Protocol (MCP) server developed for Groq, enabling interaction with Groq via the command line. It allows users to invoke Groq's AI capabilities, including image analysis, text-to-speech (TTS), and speech-to-text (STT), through simple commands.

🚀 Quick Start

Quick Start with Claude Desktop

1. Obtain a Groq API Key

   • Visit https://www.groq.com and register a developer account.
   • Create a new API key in the console.

2. Install the uv Tool

   • Open a terminal and run the following command:

     uv init
     

   • Follow the prompts to complete the initialization configuration of uv.

3. Install the Groq MCP Server

   • Run the following command to install the server:

     ./scripts/install.sh
     

   • For Mac users, this command will install the Groq MCP server into the relevant configuration file in Claude Desktop (path: ~/Library/Application Support/Claude/claude_desktop_config.json). Make sure to restart or refresh Claude Desktop to apply the changes.

4. Copy the Environment Variable Example

   • Copy the .env.example file:

     cp .env.example .env
     

   • Open the .env file and add your Groq API key:

     GROQ_API_KEY=your_api_key_here
     

📦 Usage with Other MCP Clients

Install and Run the Server Using the uv Tool

1. Create a Virtual Environment and Install Dependencies

   • Run the following commands to create and activate a virtual environment:

     uv venv
     source .venv/bin/activate
     

   • Install the project dependencies:

     uv pip install -e ".[dev]"
     

2. Invoke Functions Using Scripts

   • Image Analysis:

     ./scripts/groq_vision.sh <path_to_image_file> [prompt] [temperature] [max_tokens] [output_directory]
     # Example:
     ./scripts/groq_vision.sh "./input/image.jpg" "What's in this picture?"
     

   • Text-to-Speech (TTS):

     ./scripts/groq_tts.sh "<your_text>" [voice_name] [model_name] [output_directory]
     # Example:
     ./scripts/groq_tts.sh "Hello, world!" "Arista-PlayAI"
     

   • Speech-to-Text (STT):

     ./scripts/groq_stt.sh <path_to_audio_file> [model_name] [output_directory]
     

Other Useful Scripts

• list_groq_voices.sh: List available TTS voices.
• list_groq_stt_models.sh: Display available STT models.
• groq_batch.sh: Handle batch operations.
• groq_translate.sh: Translate text or audio.

🔧 Contribution Guide

Quick Setup Installation

1. Clone the Repository

   git clone https://github.com/groq/groq-mcp-server
   cd groq-mcp
   

2. Activate the Virtual Environment and Install Dependencies

   uv venv
   source .venv/bin/activate
   uv pip install -e ".[dev]"
   

3. Copy and Configure Environment Variables

   cp .env.example .env
   # Edit the .env file and add your API key:
   GROQ_API_KEY=your_api_key_here
   

Available Scripts

Vision and Image Analysis

./scripts/groq_vision.sh <image_file> [prompt] [temperature] [max_tokens] [output_directory]
# Example:
./scripts/groq_vision.sh "./input/image.jpg" "What's in this picture?"

Text-to-Speech (TTS)

./scripts/groq_tts.sh "<text>" [voice_name] [model_name] [output_directory]
# Example:
./scripts/groq_tts.sh "Hello, world!" "Arista-PlayAI"

Speech-to-Text (STT)

./scripts/groq_stt.sh <audio_file> [model_name] [output_directory]

Development Scripts

Test Script

# Run tests:
./scripts/test.sh

🛠️ Troubleshooting and Support

If you encounter issues, check the error messages in the terminal or refer to the documentation. You can also seek help in the following ways:

• Visit https://support.groq.com to submit a ticket.
• Join Groq's developer community forum to exchange experiences with other developers.

⚠️ Important Note

Please ensure that you always use the latest API key and comply with Groq's terms and conditions of service. For assistance, refer to the official documentation or contact the support team.